{"id":"W4394591472","doi":"10.5194/tc-18-1621-2024","title":"MMSeaIce: a collection of techniques for improving sea ice mapping with a multi-task model","year":2024,"lang":"en","type":"article","venue":"˜The œcryosphere","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Environment and Climate Change Canada","keywords":"Computer science; Downscaling; Sea ice; Synthetic aperture radar; Robustness (evolution); Sea ice concentration; Data mining; Artificial intelligence; Remote sensing; Climate change; Arctic ice pack; Climatology; Geography; Oceanography; Geology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002785086,0.0001332415,0.0001422909,0.000027333,0.000246748,0.00006160513,0.0001671812,0.00007063302,0.0000867501],"category_scores_gemma":[0.00001173573,0.00008397223,0.0000698543,0.0002985275,0.0000931699,0.0001723898,0.00001312049,0.0001622744,0.000009093481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000137089,"about_ca_system_score_gemma":0.0001924916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003292589,"about_ca_topic_score_gemma":0.007078355,"domain_scores_codex":[0.9991512,0.00002387125,0.0001788125,0.0002350344,0.0001673977,0.0002437254],"domain_scores_gemma":[0.9994994,0.0001603607,0.00006879415,0.0001565056,0.00006742568,0.00004752947],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000883689,0.0001713628,0.121945,0.00407345,0.0005183651,0.00004780685,0.01363576,0.06812222,0.002486613,0.001149893,0.004979091,0.7819868],"study_design_scores_gemma":[0.0001537109,0.00015322,0.002428507,0.0001054252,0.00005346058,0.00002377511,0.0009330168,0.9933909,0.00006391586,0.0005420847,0.002013539,0.0001384195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.108973,0.000701978,0.8857443,0.0003885513,0.0002081112,0.000943392,0.0001892079,0.0002523435,0.002599095],"genre_scores_gemma":[0.9466261,0.00002855595,0.05076686,0.00011884,0.00007360311,0.00001571175,0.00003275798,0.00001025422,0.002327333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9252687,"threshold_uncertainty_score":0.4977431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01298040595924887,"score_gpt":0.2198728544407215,"score_spread":0.2068924484814727,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}